Efficient Machine Learning Classifier to Detect and Monitor COVID-19 Cases Based on Internet of Things Framework - Proposed IoT-Based Architecture

Aug 5, 2026

Upload by Himbo

An IoT-driven framework is proposed to support the early detection and ongoing monitoring of COVID-19 suspected and affected patients. Wearable and sensor devices collect symptoms data and upload it to a physician, data analytics center, cloud, and isolation or health centers. Symptom patterns from major waves and variants, including the first wave, second wave, and omicron, guide suspect identification. Five machine learning algorithms from prior literature are compared to select an efficient classifier, enabling rapid, real-world case detection and treatment/recovery monitoring while continuously collecting data for iterative improvements.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages7

Reading Time18 min

AccessFree to download

Abstract

Introduction

Method

IoT environment

Proposed architecture

Efficient machine learning classifier to detect and monitor COVID-19 cases based on internet of things framework Felcia Bel, Sabeen Selvaraj Department of Computer Science, SRM Institute of Science and Technology, Chennai, India Article history: Received Jun 2, 2022 Revised Dec 1, 2022 Accepted Dec 7, 2022 Keywords: Coronavirus disease Detection and monitoring Internet of things Machine learning algorithms Treatment history Corresponding Author: In this research work, coronavirus disease 2019 (COVID-19) has been considered to help mankind survive the present-day pandemic. This research is helpful to monitor the patients newly infected by the virus, and patients who have already recovered from the disease, and also to study the flow of virus from similar health issues. In this paper, an internet of things (IoT) framework has been developed for the early detection of suspected cases. This framework is used for collecting and uploading symptoms (data) through sensor devices to the physician, data analytics center, cloud, and isolation/health centers. The symptoms of the first wave, second wave, and omicron are used to identify the suspects. Five machine learning algorithms which are considered to be the best in the existing literature have been used to find the best machine learning classifier in this research work. The proposed framework is used for the rapid detection of COVID-19 cases from real-world COVID-19 symptoms to mitigate the spread in society. This model also monitors the affected patient who has undergone treatment and recovered. It also collects data for analysis to perform further improvements in algorithms based on daily updated information from patients to provide better solutions to mankind. This is an open access article under the CC BY-SA license. Sabeen Selvaraj Department of Computer Science, SRM Institute of Science and Technology Kattankulathur, Chennai-603203, India Email: [sabeens@srmist.edu.in](sabeens@srmist.edu.in) Article Info ABSTRACT 1. INTRODUCTION Coronavirus disease 2019 (COVID-19) is a life-threatening disease for humanity around the globe. It was a great deal for people to survive in this pandemic era. Many variants are arising from this virus frequently. Hence, covid becomes endless despite vaccinations and booster doses. As on January 18, 2022, 328,532,929 confirmed cases and 5,542,359 deaths were reported to World Health Organization (WHO) dashboard [1] . The symptoms due to alpha, delta, and gamma (delta plus) and other virus attacks are taken into consideration for the analysis to find a better internet of things (IoT) solution to mitigate the spread of diseases from future variants. The spread could also be reduced by wearing masks, social distancing, and sanitizing the hands frequently. The government has insisted that people get vaccinated to reduce the effect of this disease. The research [2], [3] are trying to find a better solution to mitigate the spread of disease rapidly based on early detection and observing new cases. The data which are collected through m-health, telehealth, and real-time patient status could be monitored [4] . A model in [5] is used to analyze the potential cases, confirmed cases, treatment given to confirmed cases, and relevant information about the virus nature for further study. IoT services provided in healthcare were previously used in existing systems [6] . Smart healthcare systems incorporate the idea of implementing health sensors and cloud technology along with IoT. These smart sensors connected to the human body are used to send and receive data actively [7] . Recently, 5G technologies are also used to connect healthcare environments using IoT [8] . In urban areas, the IoT devices connected to healthcare centers face problems such as security, and privacy. So, the IoT data is processed using a vehicular ad-hoc network (VANET) zone and evaluated using simulators [9] . To acquire patient information, wearable devices

FAQs

How does the proposed framework detect and monitor COVID-19 cases?

Wearable and sensor devices collect real-time symptom data and send it through an IoT workflow to physicians, analytics centers, cloud services, and isolation/health centers for identification and monitoring.

Which data sources and variants are used for identifying suspected cases?

The framework uses symptoms corresponding to the first wave, second wave, and omicron to identify suspected cases and support detection.

What role do machine learning algorithms play in the study?

Five machine learning algorithms selected from existing literature are evaluated to find the most efficient classifier for early diagnosis and to mitigate spread by improving decision accuracy.

Aug 5, 2026

Upload by Himbo